© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1600
    Prev
    Next
    INDEX
    Explanations

    question and answer prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rin
    -0.24
    æľįåĬ¡ä¸ļ
    -0.23
    esis
    -0.23
    _prec
    -0.23
     bais
    -0.22
     Dok
    -0.22
    çݰ代
    -0.21
    è´Łè´£ä»»
    -0.21
    å°ıæŶåīį
    -0.21
    æ®ĭçķĻ
    -0.21
    POSITIVE LOGITS
    表æī¬
    0.38
    稿件
    0.36
     prize
    0.35
    稿
    0.35
    æĬķ稿
    0.34
    æĴ°
    0.32
     prizes
    0.32
     featured
    0.32
    å¥ĸåĬ±
    0.31
    ä¼ĺç§Ģ
    0.31
    Activations Density 0.038%

    No Known Activations